© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83059
    Prev
    Next
    INDEX
    Explanations

    anglic/angiotensin/angiography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ב
    1.41
    し
    1.33
    ك
    1.29
     at
    1.23
     in
    1.20
    ש
    1.17
    \%$
    1.16
    ко
    1.14
    تها
    1.14
    였
    1.14
    POSITIVE LOGITS
    is
    1.46
    n
    1.46
    ную
    1.44
    i
    1.38
    od
    1.34
    am
    1.34
    or
    1.31
    on
    1.29
    ai
    1.29
    ное
    1.28
    Activations Density 0.000%

    No Known Activations